Machine-Learning Based Packet Switching Method for Providing Stable High-Quality Video Streaming in Multi-Stream Transmission

Broadcasting gateway equipment generally uses a method of simply switching to a spare input stream when a failure occurs in a main input stream.However,when the transmission environment is unstable,problems such as reduction in the lifespan of equipment due to frequent switching and interruption,delay,and stoppage of services may occur.Therefore,applying a machine learning(ML)method,which is possible to automatically judge and classify network-related service anomaly,and switch multi-input signals without dropping or changing signals by predicting or quickly determining the time of error occurrence for smooth stream switching when there are problems such as transmission errors,is required.In this paper,we propose an intelligent packet switching method based on the ML method of classification,which is one of the supervised learning methods,that presents the risk level of abnormal multi-stream occurring in broadcasting gateway equipment based on data.Furthermore,we subdivide the risk levels obtained from classification techniques into probabilities and then derive vectorized representative values for each attribute value of the collected input data and continuously update them.The obtained reference vector value is used for switching judgment through the cosine similarity value between input data obtained when a dangerous situation occurs.In the broadcasting gateway equipment to which the proposed method is applied,it is possible to perform more stable and smarter switching than before by solving problems of reliability and broadcasting accidents of the equipment and can maintain stable video streaming as well.

Study of Crosstalk Property in an Optical Packet Switching Node

The effect of queuing delay of output buffer on the crosstalk property in optical packet switching nodes is investigated. The relationship between crosstalk and buffer length is obtained. From the calculation and simulation results, it is concluded that the crosstalk power penalty predominantly depends on the buffer length, the longer the buffer, the greater the penalty, as well as the random range of the penalty. While comparing with the effect of queuing delay, the effect of random routing path delay takes very little proportion in the total power penalty.

Simulation of the Physical Performance of Optical Packet Switching Nodes

A graphical and visual simulation system for the study of optical packet switching (OPS) nodes is accomplished. With the simulation system, the effect on physical performance-bit error rate (BER) due to a variety of factors such as the crosstalk parameters of OPS nodes, number of cascaded OPS nodes, length of optical output buffer, traffic load and fluctuation of amplitude of optical signals are evaluated. Reliability of the simulation system is proved by the analytical results obtained in all the above cases.

An Arrangement of Channels and Transceivers in Optical Packet Switching Networks

Based on a media access and control（MAC）protocol,an arrangement of channels and transceivers in optical packet switching dense wavelength division multiplexing（DWDM）networks is proposed in this paper.In order to reduce the cost of nodes,fixed transmitters and receivers are used instead of tunable transmitters and receivers.Two fixed transmitters and many fixed receivers are used in each node in the scheme.The average waiting delay of this scheme is analyzed through mathematics and computer simulation.The result shows that the property of the scheme is almost the same as using tunable transmitter and receiver.Furthermore,if the tuning time of tunable transmitters is taken into account,the performance of the tunable transmitter scheme is poor than this scheme at the average waiting delay and throughput of the network.

ANALYSIS AND DESIGN OF THE STABLE PARALLEL PACKET SWITCH

This paper analyzes the Parallel Packet Switch(PPS) architecture and studies how to guarantee its performance. Firstly a model of Stable PPS (SPPS) is proposed. The constraints of traffic scheduling algorithms, the number of switching layers and internal speedup, for both bufferless and buffered SPPS architecture, are theoretically analyzed. Based on these results, an example of designing a scalable SPPS with 1.28T capacity is presented, and practical considerations on implementing the scheduling algorithm are discussed. Simulations are carried out to investigate the validity and delay performance of the SPPS architecture.

OPTIMIZATION OF WDM OPTICAL PACKET SWITCHES WITH SPARSE WAVELENGTH CONVERTERS AND NON-DEGENERATE FIBER DELAY-LINES

This paper investigates the untraditional approach of contention resolution in Wavelength Division Multiplexing (WDM) Optical Packet Switching (OPS). The most striking characteristics of the developed switch architecture are: (1) Contention resolution is achieved by a combined sharing of Fiber Delay-Lines (FDLs) and Tunable Optical Wavelength Converters (TOWCs); (2) FDLs are arranged in non-degenerate form, i.e., non-uniform distribution of the delay lines; (3) TOWCs just can perform wavelength conversion in partial continuous wavelength channels, i.e., sparse wavelength conversion. The concrete configurations of FDLs and TOWCs are described and analyzed under non-bursty and bursty traffic scenarios. Simulation results demonstrate that for a prefixed packet loss probability constraint, e.g., 10-6, the developed architecture provides a different point of view in OPS design. That is, combined sharing of FDLs and TOWCs can, effectively, obtain a good tradeoff between the switch size and the cost, and TOWCs which are achieved in sparse form can also decrease the implementing complexity.

A Novel Packet Switch Node Architecture for Contention Resolution in Synchronous Optical Packet Switched Networks

Packet contention is a key issue in optical packet switch (OPS) networks and finds a viable solution by including optical buffering techniques incorporating fiber delay lines (FDLs) in the switch architecture. The present paper proposes a novel switch architecture for packet contention resolution in synchronous OPS network employing the packet circulation in FDLs in a synchronized manner. A mathematical model for the proposed switch architecture is developed employing packet queuing control to estimate the blocking probability for the incoming traffic. The switch performance is analyzed with a suitable contention resolution al-gorithm through the computer simulation. The simulation results substantiate the proposed model for the switch architecture.

Research on application of MOOC in optical packet switching

An experiment on receiving and identifying multiple optical orthogonal codes （MOOC） sequence-based optical labels in an optical packet switching （OPS） network is reported. Two groups of MOOC with a code length of 23 and a code weight of 3 are used to identify the optical labels. The scheme and principle of OPS networks based on MOOC sequence-based optical labels are presented. Because optical labels contain OPS and routing information, the importance of optical label processing with multiple inconsecutive, random, and burst optical labels in an OPS network is pointed out. Considering the MOOC-based optical labels, we design a circuit consisting of a broadened network and a cascaded amplifier to receive multiple groups of low-power narrow pulses （optical labels in the MOOC-OPS network） with a period of 2 ns. The successful experimental results demonstrate that the designed scheme is feasible.

Optical Packet Routing Performance of an Optical Packet Switch With an Optical Digital/Analog-Conversion-Type Header Processor (Wavelength Label Switch)

We demonstrate the routing operation of optical packets by an optical packet switch consisting of an optical digital-to-analog conversion-type header processor, a wavelength converter using an electrically-tunable laser, and an arrayed-waveguide grating router. A packet transfer by two-bit optical header was achieved for the first time.

Improved optical packet switching structure with recirculation buffer and feedback tunable wavelength converter

The performance of an optical switching network is mainly determined by its core node structure. An improved optical packet switching （OPS） node structure based on recirculation optical fiber delay line （FDL） and feedback tunable wavelength converter （TWC）, and a specific scheduling algorithm for the node structure are presented. This switching structure supports both point-to-point and point-to-multi- points broadcasting transmission with superior capacity expansion performance. Its superiority in packet loss probability is proved by simulation.

Key Technologies for Optical Packet Switching

The paper describes our recent progress on key technologies and components for realizing optical packet switching, including an out-of-band optical label switching technique, an optical packet synchronizer and a burst-mode optical receiver.

Photonic Packet Switching Based on Optical Label Processing

We express a photonic packet switch prototype based on optical label processing methods which dramatically increase the label processing capability. We experimentally demonstrate 40Gbit/s/port packet switching and optical buffering capabilities of the prototype.

Performance Study on Priority Strategies for WDM Packet Switches under Long-Range Dependent Traffic

The impact of long-range dependent (LRD) traffic on the buffer management schemes for WDM packet switches is studied by simulation. The different priority strategies are compared. The principles of efficient strategy design are also presented.

Simulation of Optical Packet-Switched Metropolitan Area Network

This paper introduces architectures of two types optical packet switched metropolitan area networks and their media access control protocols. We have designed related network simulation systems. With these simulation systems, the characteristics and performance of the two MANs can be achieved.

A Genetic Algorithm for Routing in Packet-Switched Communication Networks

ＡＧｅｎｅｔｉｃＡｌｇｏｒｉｔｈｍｆｏｒＲｏｕｔｉｎｇｉｎＰａｃｋｅｔ┐ＳｗｉｔｃｈｅｄＣｏｍｍｕｎｉｃａｔｉｏｎＮｅｔｗｏｒｋｓＨｅＣｕｉｈｏｎｇＯｕＹｉｓｈａｎＬｉＸｉａｎｊｉ（ＧｕａｎｇｄｏｎｇＩｎｓｔｉｔｕｔｅｏｆＴｅｃｈｎｏｌｏｇｙ，Ｇｕａ...

Research on performance of multicasting in optical packet switched networks

Different multicasting schemes in optical packet switched networks are discussed, including the parallel mode, serial mode, and hybrid mode multicasting schemes. Simulated modeling technique is applied to compare the network-level performance of the three multicasting schemes. A conclusion can be drawn from the results that since the hybrid-mode multicasting scheme can increase the multicast success ratio and reduce the packet retransmission times compared with the other two schemes, it is the best choice for delivering multicasting sessions in the optical packet switched networks.

Accelerating Packet Classification with Counting Bloom Filters for Virtual Open Flow Switching

The growing trend of network virtualization results in a widespread adoption of virtual switches in virtualized environments. However, virtual switching is confronted with great performance challenges regarding packet classification especially in Open Flow-based software defined networks. This paper first takes an insight into packet classification in virtual Open Flow switching, and points out that its performance bottleneck is dominated by flow table traversals of multiple failed mask probing for each arrived packet. Then we are motivated to propose an efficient packet classification algorithm based on counting bloom filters. In particular, counting bloom filters are applied to predict the failures of flow table lookups with great possibilities, and bypass flow table traversals for failed mask probing. Finally, our proposed packet classification algorithm is evaluated with real network traffic traces by experiments. The experimental results indicate that our proposed algorithm outperforms the classical one in Open v Switch in terms of average search length, and contributes to promote virtual Open Flow switching performance.

PERFORMANCE COMPARISON OF CELL-BASED AND PACKET-BASED SWITCHING SCHEMES FOR SHARED MEMORY SWITCHES

Shared Memory (SM) switches are widely used for its high throughput, low delay and efficient use of memory. This paper compares the performance of two prominent switching schemes of SM packet switches: Cell-Based Switching (CBS) and Packet-Based Switching (PBS).Theoretical analysis is carried out to draw qualitative conclusion on the memory requirement,throughput and packet delay of the two schemes. Furthermore, simulations are carried out to get quantitative results of the performance comparison under various system load, traffic patterns,and memory sizes. Simulation results show that PBS has the advantage of shorter time delay while CBS has lower memory requirement and outperforms in throughput when the memory size is limited. The comparison can be used for tradeoff between performance and complexity in switch design.

A Network Calculus Approach for the Analysis of Packet-switching Networks

Network calculus is an evolving new methodology for backlog and delay analysis of packet-switching networks. With network calculus we are able to compute tight bounds on delays,backlogs,and effective bandwidths in a lossless setting applicable to packet-switching networks and better understand some physical properties of networks. In this paper,the basic network calculus concepts of arrival curves and service curves are introduced.Then we provide the approach for modeling leaky-bucket,generic cell rate algorithm(GCRA),constant bit rate(CBR)flow, variable bit rate(VBR) flow with arrival curve.It is shown that all rate-based packet schedulers can be by a simple rate latency service curve.And by applying these fundamental rules of network calculus,bounds on delay, buffer,effective bandwidth for leaky bucket,GCRA,CBR and VBR can be derived and some practical examples are given.Finally,we compare all the results obtained and conclude this paper.

A Service Ratio-Based Dynamic Fair Queueing Algorithm for Packet-Switching Networks

A new weighted fair queueing algorithm is proposed, which uses the novel flow-based service ratio parameters to schedule flows. This solves the main drawback of traditional weighted fair queueing algorithms-the packet-based calculation of the weight parameters. In addition, this paper proposes a novel service ratio calculation method and a queue management technology. The former adjusts the service ratio parameters adaptively based on the dynamics of the packet lengths and then solves the unfairness problem induced by the variable packet length. The latter improves the utilization of the server’s queue buffer and reduces the delay jitter through restricting the buffer length for each flow.